Teaching · University of South Florida
TTE 6267
Traffic Flow Theory
Classical traffic flow theory — kinematic waves, car-following, MFD — paired with autonomous driving, simulation (SUMO/CARLA), and modern AI techniques for traffic control.
Course overview
This course presents a comprehensive overview of vehicular traffic flow theory, emerging transportation AI technologies, and their integration in evaluating congestion and determining control strategies.
Starting from the basic concepts that define a traffic stream, the course covers the classical theories — the kinematic wave model, cellular automata, car-following models, and macroscopic traffic flow models. Beyond traditional theory, students are introduced to state-of-the-art traffic and self-driving simulation tools such as SUMO and CARLA, and to contemporary AI techniques including autonomous driving, reinforcement learning, and large language models. Their applications in traffic operations and implications for congestion management are discussed throughout.
Course outline
Chapter 1 — Time-space diagram and N-curve
- Single-vehicle dynamics
- Vehicle stream characteristics
- Delays, queueing, and travel time
Chapter 2 — Car-following models and autonomous driving
- Traditional car-following models
- Control structure and algorithms of autonomous driving
- Impact of car-following on congestion
- Design your own self-driving car
Chapter 3 — The kinematic wave model
- Shockwaves and bottlenecks
- Extensions: merges, diverges, multilane
- Numerical solutions
- Impacts of lane changes and trucks
- Control strategies: ramp metering, HOV lanes, truck lanes, variable speed limits
Chapter 4 — Variational theory
- Hamilton-Jacobi PDE
- Solutions for initial- and boundary-value problems
Chapter 5 — Macroscopic models for cities
- Macroscopic Fundamental Diagram (MFD) and reservoir models
- MFD estimation
- Percolation theory for urban networks
Chapter 6 — Machine learning for traffic control
- Deep reinforcement learning
- Opportunities and challenges of large language models
- Machine learning for complex systems
Assessment
Students choose one of two evaluation tracks at the start of the semester:
Option 1 — Exam track
- Wiki / book section contribution — 25%
- Homework — 50%
- Final exam (comprehensive) — 25%
Option 2 — Research track
- Paper — 70%
- Homework — 30%
The wiki assignment asks students to identify a section of the Wikipedia traffic flow article where they can contribute a two-page extension based on material from class.
Materials
- Textbook. Custom course text on Overleaf: https://www.overleaf.com/read/znrxktdspcvd#d3373b
- References.
- Daganzo, C. F. (1997). Fundamentals of Transportation and Traffic Operations. Pergamon-Elsevier, Oxford, U.K.
- Leutzbach, W. (1988). Introduction to the Theory of Traffic Flow.
- Traffic Flow Theory: A Monograph (TRB).
- Course site. Canvas (USF) — current-semester schedule, slides, and assignments live there.
Policies
Homework. Homework is assigned frequently and is essential to understanding the lecture material. Homework will be collected and graded. Late homework is not accepted unless arrangements are made with Dr. Zhou prior to the deadline. Homework is individual; discussion with classmates is encouraged.
Exams. Exams cover material from lectures, notes, handouts, exercises, and homework. The final exam is given on the date assigned by the university and is comprehensive. Only university-excused circumstances are considered; a grade of zero is assigned for unexcused missed exams.